Skip to content

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

License

Notifications You must be signed in to change notification settings

modelai/ymir-detectron2

 
 

Repository files navigation

detectron2-ymir

ymir docker image

  • ymir 1.1.0 docker images are compatible with ymir 1.0.0
docker pull youdaoyzbx/ymir-executor:ymir1.0.0-detectron2-tmi

build executor

docker build -t ymir/ymir-executor:ymir1.1.0-cuda111-detectron2-tmi . -f cu111.dockerfile --build-arg SERVER_MODE=dev --build-arg YMIR=1.1.0

todo

  • do not support small batch size (=2) with large learning rates (>0.001).
FloatPointError: Loss became infinite or NaN at iteration=902!
loss_dict = {'loss_cls': nan, 'loss_box_reg': nan}

change log

  • add folder ymir for utils, train, infer and mining

  • modify detectron2/engine/defaults.py default_writers to change tensorboard logging directory

  • modify detectron2/engine/hooks.py EvalHook to write monitor.txt and result.yaml

  • modify tools/train_net.py to modify training configuration

  • modify detectron2/evaluation/coco_evaluation.py to save EVAL_TMP_FILE

About

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 93.5%
  • Cuda 3.5%
  • C++ 2.5%
  • Other 0.5%